In this paper, we propose a Global-Supervised Contrastive loss (LGSupCon) and a view-aware-based post-processing (VABPP) method for the field of vehicle re-identification. The traditional supervised contrastive loss (...
详细信息
Deep convolutional neural networks (CNNs) have been widely applied for low-level vision over the past five years. According to nature of different applications, designing appropriate CNN architectures is developed. Ho...
详细信息
Magnetic resonance (MR) image acquisition is an inherently prolonged process, whose acceleration by obtaining multiple undersampled images simultaneously through parallel imaging has always been the subject of researc...
详细信息
Multi-view clustering (MVC) aims to exploit the latent relationships between heterogeneous samples in an unsupervised manner, which has served as a fundamental task in the unsupervised learning community and has drawn...
详细信息
Federated learning (FL) can be used to improve data privacy and efficiency in magnetic resonance (MR) image reconstruction by enabling multiple institutions to collaborate without needing to aggregate local data. Howe...
详细信息
In recent years, incomplete multi-view clustering, which studies the challenging multi-view clustering problem on missing views, has received growing research interests. Although a series of methods have been proposed...
详细信息
Magnetic resonance (MR) imaging is a commonly used scanning technique for disease detection, diagnosis and treatment monitoring. Although it is able to produce detailed images of organs and tissues with better contras...
详细信息
Accelerated multi-modal magnetic resonance (MR) imaging is a new and effective solution for fast MR imaging, providing superior performance in restoring the target modality from its undersampled counterpart with guida...
详细信息
Super-resolving the Magnetic Resonance (MR) image of a target contrast under the guidance of the corresponding auxiliary contrast, which provides additional anatomical information, is a new and effective solution for ...
详细信息
Recently, deep learning has been widely used in the field of vehicle re-identification. When training a deep model, softmax loss is usually used as a supervision tool. However, the softmax loss performs well for close...
详细信息
Recently, deep learning has been widely used in the field of vehicle re-identification. When training a deep model, softmax loss is usually used as a supervision tool. However, the softmax loss performs well for closed-set tasks, but not very well for open-set tasks. In this paper, we sum up five shortcomings of center loss and solved all of them by proposing a dual distance center loss (DDCL). Especially we solve the shortcoming that center loss must combine with the softmax loss to supervise training the model, which provides us with a new perspective to examine the center loss. In addition, we verify the inconsistency between the proposed DDCL and softmax loss in the feature space, which makes the center loss no longer be limited by the softmax loss in the feature space after removing the softmax loss. To be specifically, we add the Pearson distance on the basis of the Euclidean distance to the same center, which makes all features of the same class be confined to the intersection of a hypersphere and a hypercube in the feature space. The proposed Pearson distance strengthens the intra-class compactness of the center loss and enhances the generalization ability of center loss. Moreover, by designing a Euclidean distance threshold between all center pairs, which not only strengthens the inter-class separability of center loss, but also makes the center loss (or DDCL) works well without the combination of softmax loss. We apply DDCL in the field of vehicle re-identification named VeRi-776 dataset and VehicleID dataset. And in order to verify its good generalization ability, we also verify it in two datasets commonly used in the field of person re-identification named MSMT17 dataset and Market1501 dataset. The experimental results of the proposed DDCL exceed that of the softmax loss in all the four datasets we used. In the two datasets with larger number of training IDs, the experimental results of the DDCL exceed that of the combination of the softmax loss and the
暂无评论